Advertisement

Self-organizing Maps and Ancient Documents

  • Eddie Smigiel
  • Abdel Belaid
  • Hatem Hamza
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3163)

Abstract

This paper presents how Self-Organizing Maps and especially Kohonen maps can be applied to digital images of ancient collections in the perspective of valorization and diffusion. As an illustration, a scheme of transparency reduction of the digitized Gutenberg Bible is presented. In this two steps method, the Kohonen map is trained to generate a set of test vectors that will train in a supervised manner a classical feed-forward network. The testing step consists then in classifying each pixel into one class out of four by feeding directly the feed forward network. The pixels belonging to the transparency class are then removed.

Keywords

Document Image Test Vector Current Pixel Supervise Learning Method Colored Letter 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

References

  1. 1.
    André, J., Chabin, M.-A.: Les documents anciens. Document Numérique 3(1-2), Editions Hermès (1999)Google Scholar
  2. 2.
    Agüera y Arcas, B.: Temporary matrices and elemental punches in Gutenberg’s DK type. In: Jensen, K. (ed.) Incunabula and their Readers: Printing, Selling and Using Books in the Fifteenth Century, The British Library, London (2003)Google Scholar
  3. 3.
    Kenney, A.R., Rieger, O.Y.: Moving theory into practice: Digital imaging for libraries and archives (April 2000) ISBN: 0-9700225-0-6Google Scholar
  4. 4.
    Egmont-Petersen, M., de Ridder, D., Handels, H.: Image processing with neural networks – a review. Pattern Recognition 35, 2279–2301 (2002)zbMATHCrossRefGoogle Scholar
  5. 5.
    Amerijckx, C., Verleysen, M., Thissen, P., et al.: Image compression by self-organized Kohonen map. IEEE Transactions on Neural Networks 9(3), 503–507 (1998)CrossRefGoogle Scholar
  6. 6.
    Hauske, G.: A self organizing map approach to image quality. Biosystems 40(1-2), 93–102 (1997)CrossRefGoogle Scholar
  7. 7.
    Koh, J., Suk, M.S., Bhandarkar, S.M.: A multilayer self organizing feature map for range image segmentation. Neural Networks 8(1), 67–86 (1995)CrossRefGoogle Scholar
  8. 8.
    Kohonen, T.: Clustering, taxonomy and topological maps of patterns. In: Proc. 6th IAPR International Conference on Pattern Recognition, München, pp. 114–128 (1982)Google Scholar
  9. 9.
    Zheng, Y., Greenleaf, J.F., Gisvold, J.J.: Reduction of breast biopsies with a modified selforganizing map. IEEE Transactions on Neural Networks 8(6) (1997)Google Scholar
  10. 10.
    Haring, S., Viergever, M.A., Kok, J.N.: Kohonen networks for multiscale image segmentation. Image and Vision Computing 12(6), 339–344 (1994)CrossRefGoogle Scholar
  11. 11.
    Kohonen, T.: Self-Organization and Associative Memory, 2nd edn. Springer, Berlin (1987)Google Scholar
  12. 12.
    Kohonen, T.: Self-Organizing Maps, 2nd edn. Springer, Berlin (1997)zbMATHGoogle Scholar
  13. 13.
    Tan, C.L., Cao, R., Shen, P., Wang, Q., Chee, J., Chang, J.: Removal of interfering strokes in double-sided document images. In: Proc. 5th IEEE Workshop on Applications of Computer Vision, Palm Springs, CA, December 2000, pp. 16–21 (2000)Google Scholar
  14. 14.
    Cao, R., Tan, C.L., Wang, Q., Shen, P.: Segmentation and analysis of double-sided handwritten archival documents. In: Proc. 4th IAPR International Workshop on Document Analysis Systems, Rio de Janeiro, Brazil, December 2000, pp. 147–158 (2000)Google Scholar
  15. 15.
    Sauvola, J., Pietikainen, M.: Adaptative document image binarization. Pattern Recognition 33(2), 225–236 (2000)CrossRefGoogle Scholar
  16. 16.
    Wang, Q., Tan, C.L.: Matching of double-sided document images to remove interference. In: Proc. IEEE Computer Society Conf. on Computer Vision and Pattern Recognition, Hawaii, December 2001, vol. I, pp. 1084–1089 (2001)Google Scholar
  17. 17.
    Sharma, G.: Show-through cancellation in scans of duplex printed documents. IEEE Trans. Image Processing 10(5), 736–754 (2001)CrossRefGoogle Scholar
  18. 18.
    Nishida, H., Suzuki, T.: A Multiscale Approach to Restoring Scanned Color Document Images with Show-Through Effects. In: Proceedings of the Seventh International Conference on Document Analysis and Recognition, ICDAR 2003 (2003)Google Scholar
  19. 19.
    Hamza, H.: Segmentation and restoration of images of old books, LORIAGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2004

Authors and Affiliations

  • Eddie Smigiel
    • 1
  • Abdel Belaid
    • 2
  • Hatem Hamza
    • 3
  1. 1.LICIA-INSA de StrasbourgStrasbourg Cedex
  2. 2.LORIAUniversité Nancy 2, Campus ScientifiqueVandoeuvre-lès-Nancy Cedex
  3. 3.LORIACPE Lyon, domaine scientifique de la Doua.Bat 3083Villeurbane cedex

Personalised recommendations